Prediction of Remaining Life of Cutting Tool Based on DNN by LIU Sheng-hui, ZHANG Ren-jing, ZHANG Shu-li, MA Chao, ZHANG Hong-guo

“…In order to better solve the problem that the remaining life of cutting tool is difficult to predict accurately, this paper studies three aspects of the selection of monitoring indexes, the extraction of data features and the establishing of prediction models Firstly, Cutting force and vibration frequency were selected as the indirect monitoring indexes of cutting tool These two indexes can accurately reflect the state of cutting tool, and also can solve the problem that the selecting the direct monitoring indexes causes, the wear analysis results of cutting tool being too subjective in the traditional state monitoring method Secondly, feature extraction is carried out by using wavelet packet analysis, and then the entropy values of the monitoring data are obtained They are taken as the input data Thirdly, the input data are used as the training data and testing data of the prediction model based on Deep Neural Network (DNN) Finally, the simulation experiments of the prediction method are carried out by using the real data of the workshop The results show that the model can effectively predict the useful life…”
Get full text

Integrated STEM education: addressing theoretical ambiguities and practical applications by Ane Portillo-Blanco, Jenaro Guisasola, Kristina Zuza

Get full text

Novel View Synthesis of Defocused Blur Scenes Based on Neural Radiance Fields by Zhaoji Lin, Yuxin Zheng, Li Yao

“…For the problem of similar two-dimensional coordinates restricting the model to distinguish scene details in the non-focal plane background, a fine sampling weight using multiscale depth feature fusion is further proposed, and a staged optimization strategy is designed. …”
Get full text

Research on hybrid intrusion detection based on improved Harris Hawk optimization algorithm by Pengzhen Zhou, Huifu Zhang, Wei Liang

“…The algorithm introduces the singer map to initialise the population, uses multi-information fusion to obtain the best prey position, and applies the sine function-based escape energy to execute a prey search strategy to obtain the optimal subset of features. In addition, the original data is preprocessed by the k-nearest neighbour and deep denoising autoencoder (KNN-DDAE) to relieve the imbalance problem of the network traffic data. …”
Get full text

A Fire Segmentation Method with Flame Detail Enhancement U-Net in Multispectral Remote Sensing Images Under Category Imbalance by Rui Zou, Zhihui Xin, Guisheng Liao, Penghui Huang, Rui Wang, Yuhu Qiao

“…CBAM enhances flame recognition by weighting important channel features and focusing spatially on small flame areas, helping address the class imbalance problem. …”
Get full text

The Imbalanced Target Classification Method Based on Mixed Learning of Virtual and Real Data by Fengyu Yang, Peng Wang, Wutao Qin, Zhangze Liao

“…We proposes a category imbalance classification model based on mixed feature enhancement between virtual and real domains to address the class imbalance problem in maritime target classification applications. …”
Get full text

Robust tampering detection and localization of composite image by Xiao WANG, Rong ZHANG, Lijun GUO

“…Aiming at the problem of tamper detection of composite image of natural images and highly simulated computer-generated images,a method of extracting image block color and texture feature based on differential histogram and local binary texture descriptor in YCbCr color space was proposed.By training posterior probability support vector machine,the image block to be measured was identified.In the case of non-overlapping block,the approximate tampering area was general judged,then the block was discriminated by pixel in the region,ultimately the accurate location of tampering area was achieved.The experimental results show that the recognition rate of 128 dpi×128 dpi image blocks is 94.75%,which is higher than other methods.The tapering region of the synthesized image can be precisely positioned,and the rotation and scaling operation show good coercivity.…”
Get full text

Multi-channel based edge-learning graph convolutional network by Shuai YANG, Ruiqin WANG, Hui MA

“…Usually the edges of the graph contain important information of the graph.However, most of deep learning models for graph learning, such as graph convolutional network (GCN) and graph attention network (GAT), do not fully utilize the characteristics of multi-dimensional edge features.Another problem is that there may be noise in the graph that affects the performance of graph learning.Multilayer perceptron (MLP) was used to denoise and optimize the graph data, and a multi-channel learning edge feature method was introduced on the basis of GCN.The multi-dimensional edge attributes of the graph were encoded, and the attributes contained in the original graph were modeled as multi-channel.Each channel corresponds to an edge feature attribute to constrain the training of graph nodes, which allows the algorithm to learn multi-dimensional edge features in the graph more reasonably.Experiments based on Cora, Tox21, Freesolv and other datasets had proved the effectiveness of denoising methods and multi-channel methods.…”
Get full text

1D-Concatenate based channel estimation DNN model optimization method by Min LU, Zehao QIN, Zhihui CHEN, Min ZHANG, Guangxue YUE

“…In order to improve the channel estimation accuracy of DNN model in wireless communication, a DNN model optimization method based on 1D-Concatenate was proposed.In this method, Concatenate performs one-dimensional data transformation, the DNN model was introduced by hopping connection, the gradient disappearance problem was suppressed, and 1D-Concatenate was used to restore the data features lost during network training to improve the accuracy of DNN channel estimation.In order to verify the effectiveness of the optimization method, a typical DNN-based wireless communication channel estimation model was selected for comparative simulation experiments.Experimental results show that the estimated gain of the existing DNN model can be increased by 77.10% by the proposed optimization method, and the channel gain can be increased by up to 3 dB under high signal-to-noise ratio.This optimization method can effectively improve the channel estimation accuracy of DNN model in wireless communication, especially the improvement effect is significant under high signal-to-noise ratio.…”
Get full text

Few-shot Named Entity Ｒecognition for Medical Text by QIN Jian, HOU Jian-xin, XIE Yi-ning, HE Yong-jun

Get full text

MSAM：Video Question Answering Based on Multi-Stage Attention Model by LIANG Li-li, LIU Xin-yu, SUN Guang-lu, ZHU Su-xia

“…This network extracts multi-modal features such as video, audio and text and feeds these features into the multi-stage attention model (MSAM), which is able to accurately locate the video information through a stage-by-stage localization method.In order to improve the effectiveness of feature fusion, a triplemodal compact concat bilinear (TCCB) algorithm is proposed to calculate the correlation between different modal features.This network is tested on the ZJL dataset.The average accuracy rate is 54.3%, which is nearly 15% higher than the traditional method and nearly 7% higher than the exist method.…”
Get full text

A BEARING DEEP LEARNING TRANSFER DIAGNOSIS METHOD BASED ON OPTIMIZATION OF SYMMETRIC POLAR COORDINATES by WU DingHai, WANG HuaiGuang, SONG Bin, ZHANG YunQiang

“…Aiming at the problem of graphical feature representation of one-dimensional mechanical vibration signals, a bearing fault diagnosis method based on symmetric polar coordinates and residual network migration learning is proposed, which combines the powerful image classification and recognition ability of convolution neural network. …”
Get full text

DYNAMIC THRESHOLD CALCULATION METHOD FOR BEARING OF HELICOPTER SWASHPLATE BASED ON BAYESIAN INFERENCE by CONG Lei, XIONG BangShu, LI Xin Min, SUN Wei, JIN XiaoQiang

“…Firstly,the singular value decomposition was used to preprocess the vibration signal,and the influence of noise on the dynamic threshold calculation result was filtered out.Secondly,the fault frequency energy feature extracting method was used to extract the features of normal data and inner ring,outer ring and ball fault data. …”
Get full text

Improvement of the classification of intangible assets for accounting purposes by S.E. Pyrizhok, E.G. Melnik

“…The article deals with the problem issues of the classification of intangible assets for the accounting and analytical maintenance of operations with them. …”
Get full text

DOE: a dynamic object elimination scheme based on geometric and semantic constraints by Yanli Liu, Siyi Chen, Heng Zhang, Neal N. Xiong, Wei Liang

“…In this paper, we propose a dynamic object elimination algorithm that combines semantic and geometric constraints to address the problem of visual SLAM being easily affected by dynamic feature points in dynamic environments. …”
Get full text

Manet: motion-aware network for video action recognition by Xiaoyang Li, Wenzhu Yang, Kanglin Wang, Tiebiao Wang, Chen Zhang

“…Actions in videos may vary at different speeds or scales, and it is difficult to cope with a wide variety of actions by relying on a single spatio-temporal scale to extract features. To address this problem, we propose a Motion-Aware Network (MANet), which includes three key modules: (1) Local Motion Encoding Module (LMEM) for capturing local motion features, (2) Spatio-Temporal Excitation Module (STEM) for extracting multi-granular motion information, and (3) Multiple Temporal Aggregation Module (MTAM) for modeling multi-scale temporal information. …”
Get full text

ID-insensitive deepfake detection model based on multi-attention mechanism by Yuncan Sheng, Zhengrui Zou, Zongxuan Yu, Mengxue Pang, Wei Ou, Wenbao Han

“…However, existing methods frequently overlook the connection between local details and overall image features, while also failing to address the problem of implicit identity leakage. …”
Get full text

A YOLO-Based Method for Head Detection in Complex Scenes by Ming Xie, Xiaobing Yang, Boxu Li, Yingjie Fan

“…Secondly, it was found in practical operations that the original IoU function has a serious problem with overlapping detection in complex scenes. …”
Get full text

SERNet: Spatially Enhanced Recalibration Network for Building Extraction in Dense Remote Sensing Scenes by Kuikui Han, Yuanwei Yang, Xianjun Gao, Dongjie Yang, Lei Xu

“…In the first stage, the designed parallel path feature extraction architecture is used to acquire deep semantic features by the spatial path to retain spatial information and contextual path to acquire deep semantic features. …”
Get full text

Small target detection in coal mine underground based on improved RTDETR algorithm by Feng Tian, Cong Song, Xiaopei Liu

“…By introducing Deformable Attention in the coding part of the RTDETR algorithm, the deformable feature of this attention mechanism is used to improve the network’s ability to extract effective image features. …”
Get full text